Intra-modality masked image modeling: A self-supervised pre-training method for brain tumor segmentation

Liangce Qi, Weili Shi, Yu Miao, Yonghui Li, Guanyuan Feng, Zhengang Jiang

Abstract: Highlights•We applied masked image modeling to pre-train brain tumor segmentation models.•A novel pretext task is proposed to improve pre-train data efficiency.•The proposed method is effective in limited pre-training datasets and small networks.•The fine-tuned model could improve the segmentation performance.